Triple

T5961366
Position Surface form Disambiguated ID Type / Status
Subject Serra de Llevant E132644 entity
Predicate hasSettlement P1068 FINISHED
Object Son Servera
Son Servera is a coastal municipality and village on the eastern side of the island of Mallorca in Spain’s Balearic Islands.
 E558169 NE FINISHED

How this triple was built (4 steps)

Every LLM step that produced this triple, in pipeline order — named-entity classification, the disambiguation choices (the exact options shown, with the pick highlighted), and the generated description. The batch + timestamp of each is in the Provenance table below.

NER Named-entity recognition gpt-5-mini
Instruction
Given a phrase, classify it is english named entity (e.g., persons, organizations, works of art) in Latin script, or not (e.g., literals, dates, URLs, verbose phrases). For disambiguation, the statement where the phrase occurs as object is also given. Please return a JSON object with `phrase` (string, the phrase being analyzed) and `is_ne` (boolean, indicating whether the phrase is a Named Entity).
Input
Phrase: Son Servera | Statement: [Serra de Llevant, hasSettlement, Son Servera]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Son Servera
Context triple: [Serra de Llevant, hasSettlement, Son Servera]
  • A. Serer
    Serer is a Niger–Congo language spoken primarily by the Serer people of Senegal and neighboring regions.
  • B. Sebaste
    Sebaste was an ancient city in the central highlands of Samaria, refounded and expanded by Herod the Great as a major Hellenistic-Roman urban center.
  • C. Temara
    Temara is a coastal city in northwestern Morocco, situated just south of Rabat and known for its beaches and growing residential and industrial areas.
  • D. Stavrota
    Stavrota is the highest mountain peak on the Greek island of Lefkada, known for its panoramic views over the Ionian Sea.
  • E. Seirah
    Seirah is a biblical location mentioned in the Hebrew Bible as a place of refuge associated with the judge Ehud.
  • F. None of above. chosen
  • G. Unsure - the case is ambiguous/there is not enough information to decide.
NEDg Description generation gpt-5.1
Instruction
Generate a one-sentence description of the target entity. 
You are given a context triple in the form (subject, predicate, object), where the object is the target entity. 
# Instructions
Use the triple to infer relevant information about the entity. Describe the entity based on what is most defining, well-known. 
Avoid repeating the information from the triple, unless really essential.
# Response Format
Return only the sentence: "Description: [one-sentence description of the target entity]"
Input
Entity: Son Servera
Triple: [Serra de Llevant, hasSettlement, Son Servera]
Generated description
Son Servera is a coastal municipality and village on the eastern side of the island of Mallorca in Spain’s Balearic Islands.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Son Servera
Target entity description: Son Servera is a coastal municipality and village on the eastern side of the island of Mallorca in Spain’s Balearic Islands.
  • A. Serer
    Serer is a Niger–Congo language spoken primarily by the Serer people of Senegal and neighboring regions.
  • B. Sebaste
    Sebaste was an ancient city in the central highlands of Samaria, refounded and expanded by Herod the Great as a major Hellenistic-Roman urban center.
  • C. Temara
    Temara is a coastal city in northwestern Morocco, situated just south of Rabat and known for its beaches and growing residential and industrial areas.
  • D. Stavrota
    Stavrota is the highest mountain peak on the Greek island of Lefkada, known for its panoramic views over the Ionian Sea.
  • E. Seirah
    Seirah is a biblical location mentioned in the Hebrew Bible as a place of refuge associated with the judge Ehud.
  • F. None of above. chosen

Provenance (5 batches)

The batch behind each pipeline step, in order, with when it ran. Timestamps are batch-level — stages were processed in waves, so the object chain (NER → NED1 → NEDg → NED2) reads in order, but predicate / elicitation batches can sit in a different wave.

Step Stage Batch ID Status When
creating Elicitation batch_69c0086c2364819091e9fe2f58fa2517 completed March 22, 2026, 3:19 p.m.
NER Named-entity recognition batch_69c039ff421c819085fc92f0b707d31b completed March 22, 2026, 6:50 p.m.
NED1 Entity disambiguation (via context triple) batch_69c0e3e8f234819099336503a797e55b completed March 23, 2026, 6:55 a.m.
NEDg Description generation batch_69c0ebb1dcb88190a101d3c88c647b41 completed March 23, 2026, 7:28 a.m.
NED2 Entity disambiguation (via description) batch_69c0ec4d1da081909cc6320078db4e53 completed March 23, 2026, 7:31 a.m.
Created at: March 22, 2026, 4:02 p.m.